© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations that contain the letters "rec" or "cv" or "vd", or phrases relating to asking

    oai_token-act-pair · gemini-2.0-flash

    received

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.70
     الرياضيه
    -0.69
    ConstraintMaker
    -0.64
    /**
    -0.58
    igshid
    -0.56
    laway
    -0.56
    ocardium
    -0.54
    bearers
    -0.54
     Undeclared
    -0.53
     Suggest
    -0.53
    POSITIVE LOGITS
    apimachinery
    0.63
     learning
    0.56
     learns
    0.55
     learn
    0.54
    得到的
    0.54
     glean
    0.53
     collecting
    0.52
    chkin
    0.52
     seeing
    0.52
     reading
    0.52
    Activations Density 3.779%

    No Known Activations